academic-paper-reviewer
Pass
Audited by Gen Agent Trust Hub on Nov 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external, untrusted content (academic papers and PDFs) which could be used as a vector for indirect prompt injection attacks where malicious instructions are hidden within the text to manipulate the agent's behavior.
- Ingestion points: The skill accepts paper content, abstracts, and specific sections from users, including text extracted from uploaded files via a PDF tool (SKILL.md).
- Boundary markers: There are no explicit delimiters or boundary markers defined in the instructions to isolate user-supplied content from the agent's system instructions.
- Capability inventory: The skill's capabilities include text generation and PDF extraction; it does not have access to high-risk tools such as network requests, file system writes, or arbitrary command execution.
- Sanitization: The instructions do not include any guidance or mechanisms for the agent to sanitize or ignore instructions potentially embedded within the analyzed document content.
Audit Metadata